How to Use the Cradl AI MCP in AutoGen

Q: How do I integrate Cradl AI with AutoGen?

Install autogen-extmcp. Use mcpservertools with your Vinkius Streamable HTTP URL, and pass the resulting tools to your AssistantAgent constructor.

Q: Can AutoGen agents monitor Cradl AI batch processing?

They do this collaboratively. One agent polls listprocessingtasks for failures, while another compiles the successful document counts from listbatches.

Q: Do AutoGen agents understand Cradl AI models?

The McpToolAdapter converts the schema automatically. Your agents can read the output of listextractionmodels and discuss the training statuses natively.

Let AutoGen agents debate document extraction results and routing rules using the Cradl AI MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cradl AI MCP to AutoGen

Create your Vinkius account to connect Cradl AI to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Cradl AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent OCR verification

Complex documents require scrutiny. One agent triggers `extract_data_from_url` to parse a contract, while a secondary auditor agent reviews the output. They negotiate over the results. The auditor checks the confidence scores via `get_task_status` and argues for human review if the numbers fall below a specific threshold.

Debate MCP Server workflow changes

Changing document routing rules impacts production. A configuration agent pulls current settings using `get_flow_details` to propose updates. A risk-averse agent challenges the proposal. It reviews the integration points and forces a consensus before any external system acts on the new flow structure.

Model selection by consensus

Picking the right schema matters. An explorer agent runs `search_models_by_name` to find candidates for a new batch of tax forms. Another agent pulls the metadata. By calling `get_model_details`, it compares extraction accuracy metrics and debates the explorer until they agree on the best model.

Setup guide

Set up Cradl AI MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Cradl AI tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Cradl AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cradl AI data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Cradl AI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cradl AI data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cradl AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Cradl AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Cradl AI MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with your Vinkius Streamable HTTP URL, and pass the resulting tools to your AssistantAgent constructor.

They do this collaboratively. One agent polls `list_processing_tasks` for failures, while another compiles the successful document counts from `list_batches`.

The `McpToolAdapter` converts the schema automatically. Your agents can read the output of `list_extraction_models` and discuss the training statuses natively.

You assign specific tools to different agents based on their roles. A manager agent might hold `list_workflows`, while worker agents only get access to extraction commands.

Vinkius processes all file URLs and parsed schema definitions inside a V8 Isolate Sandbox. The zero-trust architecture ensures your proprietary contracts disappear from memory the moment the HTTP transport closes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript